{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "import torch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "torch.optim.lr_scheduler.StepLR"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "getattr(torch.optim.lr_scheduler, \"StepLR\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = getattr(torch.nn, \"ReLU\")()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "loss = getattr(torch.nn, \"L1Loss\")()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "input = torch.randn(3, 5, requires_grad=True)\n",
    "target = torch.randn(3, 5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "b = torch.randn(2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a(b)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "output = loss(input, target)\n",
    "output.backward()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tensor(1.1283)"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "torch.tensor(output.item())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s = 1.\n",
    "if s is not None:\n",
    "    assert 0.0 < s < 1.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "class A:\n",
    "    @property\n",
    "    def __name__(self):\n",
    "        return \"adafa\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a = A()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a.__name__"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from training.gpu_manager import GPUManager"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "gpu_manager = GPUManager(True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2020-07-21 14:10:13.170 | DEBUG    | training.gpu_manager:_get_free_gpu:57 - pid 11721 picking gpu 0\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "0"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gpu_manager.get_free_gpu()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pathlib import Path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "p = Path(\"/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "str(p).split(\"/\")[0] + \"/\" + str(p).split(\"/\")[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "p.parents[0].resolve()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "p.exists()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "d = 'Experiment JSON, e.g. \\'{\"dataset\": \"EmnistDataset\", \"model\": \"CharacterModel\", \"network\": \"mlp\"}\\''"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "print(d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "import yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = \"/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/sample_experiment.yml\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open(path) as f:\n",
    "    d = yaml.safe_load(f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "experiment_config = d[\"experiments\"][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'dataloader': 'EmnistDataLoader',\n",
       " 'data_loader_args': {'splits': ['train', 'val'],\n",
       "  'sample_to_balance': True,\n",
       "  'subsample_fraction': None,\n",
       "  'transform': None,\n",
       "  'target_transform': None,\n",
       "  'batch_size': 256,\n",
       "  'shuffle': True,\n",
       "  'num_workers': 0,\n",
       "  'cuda': True,\n",
       "  'seed': 4711},\n",
       " 'model': 'CharacterModel',\n",
       " 'metrics': ['accuracy'],\n",
       " 'network': 'MLP',\n",
       " 'network_args': {'input_size': 784, 'num_layers': 2},\n",
       " 'train_args': {'batch_size': 256, 'epochs': 16},\n",
       " 'criterion': 'CrossEntropyLoss',\n",
       " 'criterion_args': {'weight': None, 'ignore_index': -100, 'reduction': 'mean'},\n",
       " 'optimizer': 'AdamW',\n",
       " 'optimizer_args': {'lr': 0.0003,\n",
       "  'betas': [0.9, 0.999],\n",
       "  'eps': 1e-08,\n",
       "  'weight_decay': 0,\n",
       "  'amsgrad': False},\n",
       " 'lr_scheduler': 'OneCycleLR',\n",
       " 'lr_scheduler_args': {'max_lr': 3e-05, 'epochs': 16}}"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "experiment_config"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "import importlib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "network_module = importlib.import_module(\"text_recognizer.networks\")\n",
    "network_fn_ = getattr(network_module, experiment_config[\"network\"])\n",
    "network_args = experiment_config.get(\"network_args\", {})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 784)"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(1,) + (network_args[\"input_size\"],)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer_ = getattr(torch.optim, experiment_config[\"optimizer\"])\n",
    "optimizer_args = experiment_config.get(\"optimizer_args\", {})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer_args"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "network_args"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "network_fn_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "net = network_fn_(**network_args)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "optimizer_(net.parameters() , **optimizer_args)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "criterion_ = getattr(torch.nn, experiment_config[\"criterion\"])\n",
    "criterion_args = experiment_config.get(\"criterion_args\", {})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "criterion_(**criterion_args)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "models_module = importlib.import_module(\"text_recognizer.models\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "metrics = {metric: getattr(models_module, metric) for metric in experiment_config[\"metrics\"]}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "torch.randn(3, 10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "torch.randn(3, 1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "metrics['accuracy'](torch.randn(3, 10), torch.randn(3, 1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "metric_fn_ = getattr(models_module, experiment_config[\"metric\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "metric_fn_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "2.e-3"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "lr_scheduler_ = getattr(\n",
    "    torch.optim.lr_scheduler, experiment_config[\"lr_scheduler\"]\n",
    ")\n",
    "lr_scheduler_args = experiment_config.get(\"lr_scheduler_args\", {})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\"OneCycleLR\" in str(lr_scheduler_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "datasets_module = importlib.import_module(\"text_recognizer.datasets\")\n",
    "data_loader_ = getattr(datasets_module, experiment_config[\"dataloader\"])\n",
    "data_loader_args = experiment_config.get(\"data_loader_args\", {})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_loader_(**data_loader_args)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "cuda = \"cuda:0\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import re\n",
    "cleanString = re.sub('[^A-Za-z]+','', cuda )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "cleanString = re.sub('[^0-9]+','', cuda )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'0'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cleanString"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "([28, 28], 1)"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "([28, 28], ) + (1,)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "list(range(3-1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1,)"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tuple([1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from glob import glob"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/text_recognizer/weights/CharacterModel_Emnist_MLP_weights.pt']"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "glob(\"/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/text_recognizer/weights/CharacterModel_*MLP_weights.pt\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "def test(a, b, c, d):\n",
    "    print(a,b,c,d)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "f = {\"a\": 2, \"b\": 3, \"c\": 4}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dict_items([('a', 2), ('b', 3), ('c', 4)])\n"
     ]
    }
   ],
   "source": [
    "print(f.items())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2 3 4 1\n"
     ]
    }
   ],
   "source": [
    "test(**f, d=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = \"/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/*\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "l = glob(path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "l.sort()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_124928' in l"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_124928',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_141139',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_141213',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_141433',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_141702',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_145028',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_150212',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_150301',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_150317',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_151135',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_151408',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_153144',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_153207',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_153310',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_175150',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_180741',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_181933',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_183347',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_190044',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_190633',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_190738',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_191111',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_191310',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_191412',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_191504',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0721_191826',\n",
       " '/home/akternurra/Documents/projects/quest-for-general-artifical-intelligence/projects/text-recognizer/src/training/experiments/CharacterModel_Emnist_MLP/0722_191559']"
      ]
     },
     "execution_count": 13,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "l"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "class ModeKeys:\n",
    "    \"\"\"Mode keys for CallbackList.\"\"\"\n",
    "\n",
    "    TRAIN = \"train\"\n",
    "    VALIDATION = \"validation\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "m = ModeKeys()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'train'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "m.TRAIN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([1.00000000e-05, 1.26485522e-05, 1.59985872e-05, 2.02358965e-05,\n",
       "       2.55954792e-05, 3.23745754e-05, 4.09491506e-05, 5.17947468e-05,\n",
       "       6.55128557e-05, 8.28642773e-05, 1.04811313e-04, 1.32571137e-04,\n",
       "       1.67683294e-04, 2.12095089e-04, 2.68269580e-04, 3.39322177e-04,\n",
       "       4.29193426e-04, 5.42867544e-04, 6.86648845e-04, 8.68511374e-04,\n",
       "       1.09854114e-03, 1.38949549e-03, 1.75751062e-03, 2.22299648e-03,\n",
       "       2.81176870e-03, 3.55648031e-03, 4.49843267e-03, 5.68986603e-03,\n",
       "       7.19685673e-03, 9.10298178e-03, 1.15139540e-02, 1.45634848e-02,\n",
       "       1.84206997e-02, 2.32995181e-02, 2.94705170e-02, 3.72759372e-02,\n",
       "       4.71486636e-02, 5.96362332e-02, 7.54312006e-02, 9.54095476e-02,\n",
       "       1.20679264e-01, 1.52641797e-01, 1.93069773e-01, 2.44205309e-01,\n",
       "       3.08884360e-01, 3.90693994e-01, 4.94171336e-01, 6.25055193e-01,\n",
       "       7.90604321e-01, 1.00000000e+00])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.logspace(-5, 0, base=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.018420699693267165"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.random.choice(np.logspace(-5, 0, base=10))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "ename": "ModuleNotFoundError",
     "evalue": "No module named 'tqdm.auto.tqdm'; 'tqdm.auto' is not a package",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-20-68e3c8bf3e1f>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0;32mimport\u001b[0m \u001b[0mtqdm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mauto\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtqdm\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mtqdm_auto\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'tqdm.auto.tqdm'; 'tqdm.auto' is not a package"
     ]
    }
   ],
   "source": [
    "import tqdm.auto.tqdm as tqdm_auto"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "tqdm.notebook.tqdm_notebook"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tqdm.auto.tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "def test():\n",
    "    for i in range(9):\n",
    "        pass\n",
    "    print(i)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "8\n"
     ]
    }
   ],
   "source": [
    "test()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}